search_tweets()

search_tweets("#rladies", n = 5000, include_rts = FALSE) %>% 
ts_plot("days", trim = 1L) +
  geom_point() + theme_minimal() +
  theme(plot.title = element_text(face = "bold")) +
  labs(x = NULL,  y = NULL,
    title = "Frequency of #rladies Twitter Hashtag Usage",
    caption = "\nSource: Data collected via rtweet - graphic by @mjhendrickson")

get_trends()

get_trends("washington") %>% # trends_available() to see locales
  top_n(3, tweet_volume) %>% # Pull top 3 trends by volume
ggplot() +
  geom_bar(mapping = aes(x = reorder(trend, -tweet_volume), y = tweet_volume), 
           stat = "identity") +
  scale_y_continuous(labels = comma) +
  theme(axis.title.x = element_blank()) +
  theme(axis.title.y = element_blank()) +
  labs(title = "Washington DC Twitter Trends",
       caption = "\nSource: Data collected via rtweet - graphic by @mjhendrickson")

stream_tweets()

rstats <- stream_tweets("rstats", timeout = 60 * 60) # = mins x sesc = 60 min
rstats %>%
ts_plot("mins", trim = 1L) +
  geom_point() + theme_minimal() +
  theme(plot.title = element_text(face = "bold")) +
  labs(x = NULL,  y = NULL,
    title = "Frequency of #rstats Twitter Mentions",
    caption = "\nSource: Data collected via rtweet - graphic by @mjhendrickson")

Social Network Analysis

# Get list of friends
friends <- get_friends(c("mjhendrickson", "kearneymw", "LittleMissData", "AnnaHenschel"))
# Get screen names for friends
friends_names <- lookup_users(friends$user_id)
# Add screen names to friends data
friends_list <- left_join(friends, friends_names)
friends_list <- friends_list[, c("user", "screen_name")]
# Accounts followed by users
friends_data <- table(friends_list$screen_name)
# User overlap
friends_trim <- subset(friends_list, 
                       screen_name %in% names(friends_data[friends_data >2L]))
# Create matrix
friends_matrix <- as.matrix(friends_trim)
# Plot SNA
plot(graph_from_edgelist(friends_matrix), 
     vertex.color = "grey", vertex.label.color = "black", 
     vertex.label.cex = .75, edge.curved = .25, 
     edge.color = "grey20", arrow.size = 5, arrow.width = .25)

get_timelines()

get_timelines(c("dataandme", "thomas_mock", "CMastication"), n = 5000) %>%
  filter(created_at > "2020-01-01") %>% group_by(screen_name) %>% 
ts_plot("days", trim = 1L) +
  geom_point() + theme_minimal() +
  theme(legend.position = "bottom",
    plot.title = element_text(face = "bold")) +
  labs(x = NULL, y = NULL,
    title = "Frequency of Tweets by Cool #rstats Twitter Folks",
    caption = "\nSource: Data collected via rtweet - graphic by @mjhendrickson")

get_favorites()

hadley_favs <- get_favorites('hadleywickham', n = 1000)
hadley_fav_count <- hadley_favs %>% group_by(screen_name) %>% 
                   summarize(n = n()) %>% arrange(desc(n))
hadley_fav_count %>% top_n(5, n) %>%
ggplot() +
  geom_col(mapping = aes(x = fct_reorder(screen_name, -n), y = n)) +
  scale_y_continuous(labels = comma) +
  theme(axis.title.x = element_blank()) +
  theme(axis.title.y = element_blank()) +
  labs(title = "Users Hadley Most Recently Favorited by Count",
       caption = "\nSource: Data collected via rtweet - graphic by @mjhendrickson")

Upset Plot

# Credit to @PaulCampbell91 for the borrowed code
rstaters <- c("mjhendrickson", "CMastication", "thomas_mock", 
              "kearneymw", "LittleMissData", "AnnaHenschel")
followers_upset <- map_df(rstaters, ~ get_followers(
       .x, n=100000, retryonratelimit = TRUE) %>% mutate(account = .x))
aRdent_followers <- unique(followers_upset$user_id)
binaries <- rstaters %>%
  map_dfc(~ ifelse(aRdent_followers %in% filter(
       followers_upset, account == .x)$user_id, 1, 0) %>% as.data.frame)
names(binaries) <- rstaters
upset(binaries, 
      nsets = 6, 
      main.bar.color = "SteelBlue", 
      sets.bar.color = "DarkCyan", 
      sets.x.label = "Follower Count", 
      text.scale = c(rep(1.4, 5), 1), 
      order.by = "freq")

But wait - there’s more!

For a full list of what’s included in the data pull, go to the Tweet Data Dictionary

A few of interest:

• created_at = UTC time of Tweet
  • df$created_at - 18000 # 5 hours in seconds for Eastern Time
• text = content of the Tweet
• source = utility used to post the Tweet
• is_retweet = TRUE/FALSE if this was a re-tweet
• favorite_count = number of times the Tweet was favorited
• retweet_count = number of times the Tweet was re-tweeted
• hashtags = string of all hashtags used
• urls_url = string of all urls
• mentions_screen_name = string of screen_names mentioned
• Fields on re-tweets, geolocation, user info

All available fields

print(colnames(search_tweets("#rladies", n = 1, include_rts = FALSE)))
#>  [1] "user_id"                 "status_id"              
#>  [3] "created_at"              "screen_name"            
#>  [5] "text"                    "source"                 
#>  [7] "display_text_width"      "reply_to_status_id"     
#>  [9] "reply_to_user_id"        "reply_to_screen_name"   
#> [11] "is_quote"                "is_retweet"             
#> [13] "favorite_count"          "retweet_count"          
#> [15] "quote_count"             "reply_count"            
#> [17] "hashtags"                "symbols"                
#> [19] "urls_url"                "urls_t.co"              
#> [21] "urls_expanded_url"       "media_url"              
#> [23] "media_t.co"              "media_expanded_url"     
#> [25] "media_type"              "ext_media_url"          
#> [27] "ext_media_t.co"          "ext_media_expanded_url" 
#> [29] "ext_media_type"          "mentions_user_id"       
#> [31] "mentions_screen_name"    "lang"                   
#> [33] "quoted_status_id"        "quoted_text"            
#> [35] "quoted_created_at"       "quoted_source"          
#> [37] "quoted_favorite_count"   "quoted_retweet_count"   
#> [39] "quoted_user_id"          "quoted_screen_name"     
#> [41] "quoted_name"             "quoted_followers_count" 
#> [43] "quoted_friends_count"    "quoted_statuses_count"  
#> [45] "quoted_location"         "quoted_description"     
#> [47] "quoted_verified"         "retweet_status_id"      
#> [49] "retweet_text"            "retweet_created_at"     
#> [51] "retweet_source"          "retweet_favorite_count" 
#> [53] "retweet_retweet_count"   "retweet_user_id"        
#> [55] "retweet_screen_name"     "retweet_name"           
#> [57] "retweet_followers_count" "retweet_friends_count"  
#> [59] "retweet_statuses_count"  "retweet_location"       
#> [61] "retweet_description"     "retweet_verified"       
#> [63] "place_url"               "place_name"             
#> [65] "place_full_name"         "place_type"             
#> [67] "country"                 "country_code"           
#> [69] "geo_coords"              "coords_coords"          
#> [71] "bbox_coords"             "status_url"             
#> [73] "name"                    "location"               
#> [75] "description"             "url"                    
#> [77] "protected"               "followers_count"        
#> [79] "friends_count"           "listed_count"           
#> [81] "statuses_count"          "favourites_count"       
#> [83] "account_created_at"      "verified"               
#> [85] "profile_url"             "profile_expanded_url"   
#> [87] "account_lang"            "profile_banner_url"     
#> [89] "profile_background_url"  "profile_image_url"

References

• Kearney MW (2019). “rtweet: Collecting and analyzing Twitter data.” Journal of Open Source Software, 4(42), 1829. doi: 10.21105/joss.01829, R package version 0.7.0, https://joss.theoj.org/papers/10.21105/joss.01829.
• Rudis, B (2018). “21 Recipes for Mining Twitter with rtweet” https://rud.is/books/21-recipes/
• Ellis, Laura (2019). “Set Analysis: A face off between Venn diagrams and UpSet plots.” https://www.littlemissdata.com/blog/set-analysis
• Upset vignette
• Kearney MW (2018). “R: Collecting and Analyzing Twitter Data.” - Specifically Slide 36 on SNA. https://github.com/mkearney/nicar_tworkshop
• Twitter Data Dictionary
• rtweet GitHub repository
• Headshot by Maureen Porto Photography
• No way gif by memecrunch
• Social media icons by iconmonstr